DeepCFL: Deep Contextual Features Learning from a Single Image
This addresses the need for unsupervised, data-independent methods in low-level vision tasks, though it appears incremental compared to existing approaches like deep image prior and SinGAN.
The paper tackles the problem of performing image synthesis and restoration without relying on external training data by proposing DeepCFL, a single-image GAN framework that learns contextual features from the input image, achieving results in tasks like outpainting, inpainting, and pixel restoration.
Recently, there is a vast interest in developing image feature learning methods that are independent of the training data, such as deep image prior, InGAN, SinGAN, and DCIL. These methods are unsupervised and are used to perform low-level vision tasks such as image restoration, image editing, and image synthesis. In this work, we proposed a new training data-independent framework, called Deep Contextual Features Learning (DeepCFL), to perform image synthesis and image restoration based on the semantics of the input image. The contextual features are simply the high dimensional vectors representing the semantics of the given image. DeepCFL is a single image GAN framework that learns the distribution of the context vectors from the input image. We show the performance of contextual learning in various challenging scenarios: outpainting, inpainting, and restoration of randomly removed pixels. DeepCFL is applicable when the input source image and the generated target image are not aligned. We illustrate image synthesis using DeepCFL for the task of image resizing.